nickboucher / imperceptible

Related projects: ⓘ

• lancopku / SOS
  Code for the paper "Rethinking Stealthiness of Backdoor Attack against NLP Models" (ACL-IJCNLP 2021)
  ☆21Updated 2 years ago
• alps-lab / trojan-lm
  TrojanLM: Trojaning Language Models for Fun and Profit
  ☆15Updated 3 years ago
• RishabhMaheshwary / hard-label-attack
  Natural Language Attacks in a Hard Label Black Box Setting.
  ☆40Updated 3 years ago
• thunlp / HiddenKiller
  Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"
  ☆37Updated 2 years ago
• PurduePAML / PICCOLO
  ☆23Updated last year
• lishaofeng / NLP_Backdoor
  Hidden backdoor attack on NLP systems
  ☆45Updated 2 years ago
• reza321 / T-Miner
  ☆17Updated 6 months ago
• thunlp / StyleAttack
  Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"
  ☆41Updated last year
• xlhex / extract_and_transfer
  ☆9Updated 3 years ago
• lancopku / Embedding-Poisoning
  Code for the paper "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models" (NAACL-…
  ☆34Updated 3 years ago
• facebookresearch / text-adversarial-attack
  Repo for arXiv preprint "Gradient-based Adversarial Attacks against Text Transformers"
  ☆98Updated last year
• xinleihe / toxic-prompt
  ☆16Updated 10 months ago
• thunlp / OpenBackdoor
  An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)
  ☆148Updated last year
• ShannonAI / backdoor_nlg
  ☆13Updated 3 years ago
• RockyLzy / TextDefender
  codes for "Searching for an Effective Defender:Benchmarking Defense against Adversarial Word Substitution"
  ☆30Updated 10 months ago
• AI-secure / Meta-Nerual-Trojan-Detection
  ☆60Updated 3 years ago
• thunlp / ONION
  Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"
  ☆28Updated 2 years ago
• thunlp / BkdAtk-LWS
  Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"
  ☆15Updated 3 years ago
• iliaishacked / sponge_examples
  ☆20Updated 2 years ago
• praateekmahajan / TrojanNN-Pytorch
  Implementation of https://github.com/PurduePAML/TrojanNN
  ☆9Updated 5 years ago
• neulab / RIPPLe
  Code for the paper "Weight Poisoning Attacks on Pre-trained Models" (ACL 2020)
  ☆137Updated 3 years ago
• leix28 / prompt-universal-vulnerability
  Implementation of the paper "Exploring the Universal Vulnerability of Prompt-based Learning Paradigm" on Findings of NAACL 2022
  ☆26Updated 2 years ago
• joey1993 / bert-defender
  codes for paper "learning to discriminate perturbations for blocking adversarial attacks in text classification" in EMNLP19
  ☆15Updated 4 years ago
• Huiying-Li / blacklight
  ☆14Updated 2 years ago
• PurduePAML / DBS
  ☆13Updated 2 years ago
• Hazelsuko07 / TextHide
  TextHide: Tackling Data Privacy in Language Understanding Tasks
  ☆30Updated 3 years ago
• tianshuocong / TePA
  [S&P'24] Test-Time Poisoning Attacks Against Test-Time Adaptation Models
  ☆14Updated 7 months ago
• papersPapers / BadPrompt
  Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"
  ☆32Updated 2 months ago
• usnistgov / trojai-literature
  ☆133Updated 4 months ago
• csong27 / collision-bert
  ☆28Updated 3 years ago